AI engineering glossary · AI ethics law product
What is post-hoc explanation?
Post-hoc explanation: An explanation produced after a model is trained, by probing the model rather than by reading its structure. Methods such as LIME, SHAP and saliency maps approximate why the model behaved as it did, but they are approximations and may not reflect the true internal reasoning.
Post-hoc explanation: an example
After training a complex churn model, a team applies SHAP to see which features pushed one customer's prediction up.
Related terms
More AI ethics law product terms
- Predictive parity
- Privacy budget
- Privacy by design
- Prohibited AI practices
- Protected attribute
- Proxy variable
- Pseudonymization
- Purpose limitation
Where you learn it
Post-hoc explanation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.